Commit Graph

179 Commits

Author SHA1 Message Date
hoshi-hiyouga
94803d8133 [model] add mistral small models (#6786) 2025-02-01 04:31:38 +08:00
hoshi-hiyouga
999c7c8fe0 [model] add qwen2.5 vl models (#6779) 2025-01-31 03:00:29 +08:00
hoshi-hiyouga
15357cdad9 [breaking] support transformers 4.48 (#6628) 2025-01-31 01:36:33 +08:00
hoshi-hiyouga
45e68b9f09 [webui] improve webui & reasoning mode (#6778) 2025-01-31 00:09:21 +08:00
qvlehao
28417f862a [model] add deepseek-R1 & show think process (#6767) 2025-01-29 12:16:26 +08:00
hoshi-hiyouga
7a04021d04 [optim] clean apollo (#6645)
* clean apollo code

* update readme
2025-01-15 01:42:50 +08:00
zhuHQ
d9189f9f0b [optim] add support to APOLLO (#6617) 2025-01-15 00:24:56 +08:00
Haian Huang(深度眸)
deacc00b12 Support InternLM3 Dense 8B Model (#6640)
* support internlm3

* update

* update

* update

* add hint
2025-01-14 18:07:27 +08:00
Zhangchi Feng
c3fda5046d Support new features of MiniCPM-V (#6626)
* fix template name

* tiny fix

* support minicpm-o-2.6
2025-01-14 00:26:19 +08:00
Zhangchi Feng
3077f20339 Fix template name of MiniCPM-V (#6620)
* fix template name

* tiny fix
2025-01-13 16:46:48 +08:00
Zhangchi Feng
fc045d7dd8 Merge branch 'main' into minicpmv 2025-01-10 20:12:07 +08:00
hiyouga
ae16ea755d improve template, add phi4 model 2025-01-09 18:27:54 +00:00
hiyouga
47e17dd689 imporve log 2025-01-08 09:56:10 +00:00
hiyouga
d8cac6f546 refactor ray integration, support save ckpt 2025-01-07 09:39:10 +00:00
Zhangchi Feng
ab87bd6b13 Merge branch 'hiyouga:main' into minicpmv 2025-01-04 11:20:33 +08:00
fzc8578
79c2d7090c add some 2025-01-04 11:11:15 +08:00
hiyouga
4b8add7287 update model name 2025-01-02 12:19:21 +00:00
hiyouga
67442bd497 add gpt2 model 2025-01-02 12:07:38 +00:00
hiyouga
e67b9dcc3a add deepseek3 model 2024-12-30 13:39:20 +00:00
hiyouga
6f5bb3b8e5 fix #6482 2024-12-30 06:03:07 +00:00
hiyouga
ee0e400f41 add qvq #6439 2024-12-25 07:52:41 +00:00
hiyouga
8fd38d273e update readme 2024-12-23 14:08:59 +00:00
hoshi-hiyouga
c23a4d0658 Merge pull request #5922 from Tuyohai/main
support granite3 models
2024-12-23 16:46:02 +08:00
hiyouga
d3509050dc add paligemma2 2024-12-18 08:57:26 +00:00
hoshi-hiyouga
015f213788 Merge pull request #6313 from ge-xing/main
support telechat2 model
2024-12-18 16:16:17 +08:00
hiyouga
b24ae55ebf support llama3 tool prompt 2024-12-17 15:52:37 +00:00
zhaohu xing
04f19ed0f3 support telechat2 model 2024-12-17 12:15:33 +00:00
hiyouga
2d107d3aef generalized packing & fix #6343 2024-12-17 10:26:19 +00:00
hiyouga
1324d158f9 support batch infer in vllm 2024-12-04 13:50:00 +00:00
hiyouga
68a612115a add qwq 2024-11-28 08:50:57 +00:00
hiyouga
ec9ff8caa2 add skywork o1 2024-11-27 05:51:59 +00:00
hiyouga
17afb7d410 add marco-o1 and openo1 dataset 2024-11-27 04:20:23 +00:00
hiyouga
b0ccc2ee86 set dev version 2024-11-25 01:36:49 +08:00
hiyouga
d622f8fdec release v0.9.1 2024-11-24 23:48:41 +08:00
hiyouga
446441fdb0 fix inputs 2024-11-23 18:26:02 +00:00
marko1616
3f2c056253 Support llama3.2vl. 2024-11-23 16:07:35 +00:00
hoshi-hiyouga
bd639a137e Merge pull request #6078 from wtmlon/support-efficient-tokens-calculation
support effective tokens calculation on sft/dpo
2024-11-20 13:43:15 +08:00
Ting
40627c601e code refactor 2024-11-19 20:33:18 +08:00
hiyouga
431ac4892c add qwen-coder and opencoder 2024-11-15 21:48:38 +08:00
hiyouga
c5fae465ec update datasets version 2024-11-04 07:52:26 +00:00
steven
6eefb4d7d2 support granite3 models 2024-11-04 10:35:03 +08:00
hiyouga
2e843d989e fix phi3 template 2024-11-02 21:31:23 +08:00
hoshi-hiyouga
c58cc22d06 Merge pull request #5910 from Cuiyn/index
Support Index series models.
2024-11-02 20:16:54 +08:00
Cuiyn
ecca9db66b fix: rename to Index-1.9B-Charater-Chat and Index-1.9B-Chat-32K 2024-11-02 20:04:14 +08:00
hiyouga
c38aa29336 support rank0 logger 2024-11-02 18:31:04 +08:00
Cuiyn
a15a69ab44 Add support for Index 2024-11-02 13:45:27 +08:00
hiyouga
30567a1487 fix incorrect loss value for vlms 2024-10-30 08:56:46 +00:00
Kingsley
67f59579d7 Merge branch 'hiyouga:main' into pixtral-patch 2024-10-29 21:01:25 +08:00
hiyouga
ae045c884f fix #5747 2024-10-29 10:47:04 +00:00
hiyouga
21db8ed2f4 use pre-commit 2024-10-29 09:07:46 +00:00